Track 1 sessions are for All Levels
Track 2 sessions are Expert/Practitioner LevelConference Day 1: Wednesday, March 20, 2013
Registration & Networking Breakfast
Conference Chair Welcome Remarks
Speaker: Richard Boire, Conference Chair, Predictive Analytics World Toronto
Diamond Sponsor Presentation
Wading Into Big Data Waters: When to Tread Lightly and When to Dive In
"Big Data" – By now, you know it's big news – perhaps bigger, even, than the name suggests. Big data refers not only to the historic influx of structured and non-structured data from non-traditional sources, but also to the big questions facing organizations wading into big data waters: How do we store, analyze and harness this data? Will it really change how we understand and respond to customers? And when should you be cautious about Big Data?
Join Jane Griffin as she shares how organizations can corral on big data to enable business decisions and bring agility to their business intelligence.
Speaker: Jane Griffin, Executive Advisor, Deloitte Canada
9:20-10:10am • Room: 713
Keynote
The Challenge of Data (Big or Small) in Predictive Analytics
Big Data is the latest buzzword in business circles today. How do we deal with exploding volumes of data? The world of predictive data analytics and data mining has always dealt with big data but the digital world and social media have increased this to a new scale. Are there disciplines and practices that deal with analytics of big data? More importantly, how differently do practitioners need to evolve their practices to reflect the new reality?
This session will look at how practitioners integrate the Big Data practices of the "old world" vs. the "new world." For example, what are the types of "Big Data" practices that have been consistently applied in predictive analytics projects over the last 20 years and which are currently still reliable today? Yet, practitioners need to also ware of new practices and approaches that attempt to meet this increasing demand for more time-sensitive solutions particularly within the social media space. Finally, this session will look at how practitioners should draw on their knowledge of the old and the new data environments in order to identify what makes sense in delivering solutions within this new frenetic environment.
Speaker: Richard Boire, Founding Partner, Boire Filler Group
[ Top of this page ] [ Agenda overview ]
Exhibits & Morning Coffee Break
10:40-10:50am • Room: 713
Gold Sponsor Presentation
Analytics & Crunching the Future
This 7-8 minute presentation will provide a non-industry specific overview on where analytics has come from, up to present day, with a vision to the future. The presentation will touch on the impact and implications that Big Data has had on the Analytic community and the resulting technological response from vendors in the form of High Performance Analytics and data visualization
Speaker: Stuart Rose, Global Insurance Marketing Manager, SAS Institute
Track 1: Churn ModelingCase Study: Data Insight Group
Divide and Conquer: Enhancing Predictions through Segmentation
This session explores how segmentation and modeling can be integrated to achieve better business results. At the same time, the session explores when it does and does not make sense to build a multi-model approach within multiple segments where reduction of churn is the ultimate business objective.
Track 2: Financial Services
Case Study: Scotiabank
Mortgage Liquidation Model Building and Application
The purpose of development of a mortgage liquidation model is to enable Group Treasury and Asset Liability Management to reduce cash flow uncertainty and improve budgeting and hedge effectiveness. A multinomial logistic regression model was built to predict two mortgage events: full payment and early renewal. The model was vetted by the validation team, and applied to cash flow analysis and gap reporting.
Wenlei Shi, Manager, Statistical Analysis, Scotiabank
[ Top of this page ] [ Agenda overview ]
Track 1: Spam DetectionCase Study: MailChimp.com
Monkeys & Math: How MailChimp Catches Bad Guys
Hear from MailChimp's Chief Scientist John Foreman as he dishes on dirty data and demonstrates the latest in MailChimp's anti-abuse artificial intelligence. MailChimp sends 3 billion emails a month for their millions of users, and they can't afford to let a drop of spam go out. Learn how the company is using cutting edge NoSQL solutions and predictive models to leave the bad guys out in the cold.
Thought LeadershipMy Five Predictive Analytics Pet Peeves
Predictive Analytics (PA) has become increasingly mature as a technical discipline over the past decade in part because it stands on the shoulders of the related disciplines of data mining and machine learning. However, there are recurring themes that permeate discussion boards and conferences that have become my personal pet peeves. This talk examines five of them and why they matter to practitioners, including why we must have humility in how far data science and algorithms can take us, and the value of business objectives, measuring "success," and measuring "significance."
Speaker: Dean Abbott, President, Abbott Analytics, Inc.
[ Top of this page ] [ Agenda overview ]
Lunch / Exhibits
1:30-2:15pm • Room: 713
Special Plenary Session
Becoming an Ace with a Robot as your Wingman!
Humans and computers have strengths that are more complementary than alike – to the point where a sophisticated algorithm may be the best "2nd person" to put on a complex task. Yet, our and computer analytic weaknesses are surprisingly severe. To explore how to improve the man/machine partnership, we compare and contrast natural and artificial intelligence, with special attention to the growing realization of how challenging it is to think truly rationally.
[ Top of this page ] [ Agenda overview ]
Lightning Round of 2-Minute Sponsor Presentations 
Track 1: MilitaryCase Study: RITRE
The New Intelligence Tradecraft: Case Studies of Activity Based Intelligence Enabled by the Application of Predictive Analytics Tools on Big Data - a Discussion of Experience and Future Potential
Military Intelligence has been one of the leading areas in the application of analytical processes to predict events. Previously, the analyst would assess and compare bits and pieces of raw information, and synthesize findings into an intelligence product to reflect enemy capabilities and vulnerability. In an era of rapidly multiplying data sources and data volumes, the pace of innovation has expanded dramatically and outcomes are optimized when decision makers experience a shared situational awareness which is enriched when we are able to leapfrog into the world of predictive analytics by exposing and aligning data streams in near real time.
Track 2: Brand Analytics
Case Study: Dell
The Illusive Brand: How to Measure Brand and the Communications Focused On It
Measuring a brand health is very difficult and can be convoluted. Often, if you have multiple metrics such as NPS or survey results, they will not align on how your brand health is changing. Helping business leaders understand how they can impact brand health is even more difficult. Natalie will present ideas on how to model out marketing's impacts on the brand, measuring the long-term impacts of an overriding campaign, and how to handle differing trends from various brand health metrics. In addition, we will discuss how to explain these models and their errors to decision makers.
[ Top of this page ] [ Agenda overview ]
Exhibits & Afternoon Break
[ Top of this page ] [ Agenda overview ]
Track 1: Brand AnalyticsCase Study: a Fortune 500 Company
Using Attitudinal Behaviour to Determine Media Spend
With one of their clients being a key manufacturer of diapers, this organization demonstrated how data could be used to determine their key areas of media spend. In targeting their efforts to Moms, the organization redefined their target segment as the Ultra Value Conscious Mom. Data was then used to determine the ideal media that contained more consumers who fit the Ultra Value Conscious Mom.
Track 2: Insurance
Case Study: Broadspire
To Sue or Not to Sue: Predicting Litigation Risk
Litigation is a major cost factor in handling casualty claims. Follow the development and testing of a "double barreled" litigation prediction application for our claims system and our parallel e-Triage system, which provides a richer data environment for certain types of insurance claims. This is a major enhancement of a robust predictive system now in use for over six years and an expansion of predictive know-how to control claim costs. See how we apply our continuous improvement philosophy to making predictive analytics a core competency inside an industry leading claims service.
Bangalore Gunashakar, Senior Technical Consultant, Broadspire
Sergo Grigalashvili, VP Architecture, Analytics, GSR, Crawford & Company
[ Top of this page ] [ Agenda overview ]
Panel Discussion
Predictive Analytics in Insurance Risk
Moderator: Stuart Rose, Global Insurance Marketing Manager, SAS Institute
At this session, three Canadian seasoned insurance practitioners give their view-point from an actuarial perspective, advanced analytics perspective and business perspective on the importance of predictive analytics in insurance risk. The discussion will focus on the data challenges, underwriting challenges, on the regulatory challenges in using these tools for pricing, as well as data challenges in building predictive analytics solutions and challenges related to developing effective underwriting strategies
Hashmat Rohian, AVP Research & Development, Aviva Canada
Colin Smith, Vice President of Operations, Opta Information Intelligence
[ Top of this page ] [ Agenda overview ]
Reception / Exhibits
[ Top of this page ] [ Agenda overview ]
Conference Day 2: Thursday, March 21, 2013
Registration & Networking Breakfast
Conference Chair Welcome Remarks
Speaker: Richard Boire, Conference Chair, Predictive Analytics World Toronto
Keynote
Enabling Data Driven Marketing in a Digital and Social World
The world of marketing, technology and data management has never been so complex and the need to deepen the integration across these functions is accelerating at an unprecedented rate. But do new forms of data, both structured and unstructured, create an opportunity to improve our decision science, develop more meaningful relationships with Customers and enhance shareholder returns? Is the explosion of data and multiple digital devices for each individual an opportunity or a risk for the models that we have and for Marketers of the future?
This session will focus on digital marketing and examine how American Express is exploring new approaches to better understand and answer the above questions. It will also illustrate how American Express is analyzing multi-channel marketing attribution and articulate how American Express is refining internal processes and platforms to become best in class digital Marketers. Lastly, it will look to illustrate new opportunities to integrate data into ongoing processes and highlight the importance of leveraging traditional and non-traditional approaches in both test design and the collection of Consumer insights.
[ Top of this page ] [ Agenda overview ]
Exhibits & Morning Coffee Break
Track 1: Recruitment Analytics
Case Study: Talent Analytics
Using Analytics to Build Your Analytics Bench: Announcing 2012 Analytics Professionals Study Results
Many innovative businesses and IT organizations appreciate the competitive advantage analytics capabilities can provide and have ambitions to reach increasing levels of analytics maturity. However, the well-documented shortage of analytic talent leaves many firms without a strong analytic talent bench and little knowledge about how and where to find analytics professionals needed to get there. In this presentation, Greta Roberts will discuss results from a major 2012 Study of Analytics Professionals that crosses industries, experience and skills. Practical insights shared include key best practices, trends and correlations that lend unexpected insight into building a strong and scalable analytic talent bench.
Speaker: Greta Roberts, Faculty Member, International Institute for Analytics
Track 2: Retail
Case Study: MakePlain/Boire Filler Group
The Exploding World of Data: The Retail Impact
With the ever-abundance of data in the retail world, how do we make sense of it. With hundreds of millions of transactions being the typical norm, retailers need to be nimble to use this information effectively. From this case study, we learn how a certain analytical approach complemented with certain tools quickly enabled this organization to make effective decisions.
[ Top of this page ] [ Agenda overview ]
Track 1: Big Data Analytics
Case Study: Precog
The Productization of Predictive Analytics
Many companies are using the predictive analytics to forecast and optimize internal business processes. However, for companies possessing large amounts of proprietary data, there is another way to leverage predictive analytics: leveraging predictive models to create new data products and incorporate data-driven features inside existing products. In this presentation, data productization expert John A. De Goes provides an introduction to productizing predictive analytics, including case studies of companies finding innovative ways to monetize their data assets via productization of predictive models. John also discusses tools and technologies that are typically required to perform productization in today's big data world.
Speaker: John De Goes, CEO and CTO, Precog
11:40am–12:25pm • Room: 711
Track 2: Net LiftCase Study: Pitney Bowes
Uplift Modeling in Theory & Practice
During this session, we'll review the current state of the art in "uplift modeling" - the practice of modeling the change in behavior that results directly from a specific treatment such as a marketing intervention. We will discuss approaches to variable selection, model construction, quality metrics and post-campaign success measurements, all of which require changes from traditional modeling practices. We'll illustrate with practical examples from demand-stimulation and customer retention applications, and highlight potential pitfalls to avoid.
[ Top of this page ] [ Agenda overview ]
Lunch
Plenary Session
Case Study: Sport Analytics Institute
Succeeding with Analytics in Professional Hockey - Now and Into the Future
This talk will cover a range of topics related to successfully using analytics in NHL organizations. Using examples from his experience, Dan MacKinnon, Director of Player Personnel of the Pittsburgh Penguins, will discuss the changing culture and evolution of analytics in hockey and how he incorporates data and analytics into his day-to-day role of evaluating future talent and managing existing player personnel. Mike Boyle, Co-founder of the Sports Analytics Institute and Assistant Professor of Information Systems at the University of Utah, will discuss how best practices for achieving success with analytics in other industries can be similarly applied within NHL organizations. Kevin Mongeon, also Co-founder of the Sports Analytics Institute and Assistant Professor of Economics at the University of New Haven, will discuss the difference between analytics in hockey compared to other sports and how appropriate use of the data is key to achieving accurate results. Together the group will discuss the future of data and analytics within NHL organizations and into the broader elite hockey system.
Mike Boyle, Co-Founder, Sports Analytics Institute
Dan MacKinnon, Director of Player Personnel, Pittsburgh Penguins
[ Top of this page ] [ Agenda overview ]
Panel Discussion
What is Big Data Analytics: A Canadian Perspective
Moderator: Richard Boire, Conference Chair, Predictive Analytics World
During this session, three of the very most seasoned Canadian practitioners give their perspective on Big Data and ultimately data itself. The discussion's focus on data will yield insights on how practitioners need to think about analytics in this new data paradigm.
Rupen Seoni, Vice President, Practice Leader, Environics Analytics
Paul Tyndall, Advanced Analytics Team Lead, RBC
[ Top of this page ] [ Agenda overview ]
3:15-3:50pm • Room: Foyer
Exhibits & Afternoon Break
[ Top of this page ] [ Agenda overview ]
Track 1: Data Visualization
Unlocking the Voice of Your Customer Through Text Analytics
Key topics I'll cover include:
- The potential new sources of client data which text analytics allows you to leverage
- What types of data elements are available and how to use them
- Opportunities to integrate Voice of the Client data with traditional data to enhance your predictive analytics
- Potential challenges with Text Analytics to consider
3:50–4:35pm • Room: 711
Track 2: Recruitment AnalyticsCase Study: Monster Worldwide
Win With Advanced Analytics
Monster was the pioneer in the online recruitment industry. To maintain its competitive advantage, it has taken the data-driven road using research, business intelligence and predictive analytics and text analytics. Join this session to hear how Monster went from good to great using business analytics to support its overall decision-making process across all regions. Jean-Paul Isson will provide highlights from his new book, "Major Steps to Win with Analytics with the Big Data." He will also discuss Monster's success with increasing customer retention, market share and customer profitability, while managing competition from paid sites, free sites and social networks.
[ Top of this page ] [ Agenda overview ]
Track 1: Churn Modeling
Case Study: Paychex
Customer Retention: Pulling the Needle from the Haystack
In these economic times, it is critical for businesses to have a stronghold on client retention, with businesses excelling in this arena better positioned for long-term success. To optimize the value of retention efforts, it's essential to understand which clients are the best fit for retention campaigns. In this session, we will review how Paychex leveraged two existing models, Paychex Attrition Model and a custom-built Lifetime Value Model, to create a Retention Tracking System (RTS). Since being deployed across the entire branch network, the RTS has become an invaluable resource as offices nation-wide strive to meet, and exceed, retention goals.
Tom Kern, Risk Modeling Analyst, Paychex, Inc.
4:40-5:30pm • Room: 713
Track 2: Financial ServicesCase Study: TD Bank
Marketing Predictive Models (Response, Survival and Premium Models) for Credit Card Insurance
This session will present marketing predictive models that are based on the customer willingness to buy credit card insurance and could help marketers to identify the life expectancy and the expected lifetime premium. This case study improves decision-making processes, resulting in more profitable and efficient operations.
Dr. Dragos Calitoiu, Senior Modeler, TD Bank Group Canada
[ Top of this page ] [ Agenda overview ]
